Title :
Learning optimal switching policies for path tracking tasks on a mobile robot
Author :
Wang, Yunqing ; Thibodeau, Bryan ; Fagg, Andrew H. ; Grupen, Roderic A.
Author_Institution :
Dept. of Comput. Sci., Massachusetts Univ., Amherst, MA, USA
Abstract :
A set of impedance controllers is used for both state estimation and tracking control on a mobile robot. State estimation is based on the states of a family of impedance controllers and tracking is implemented through a single controller from this set. Reinforcement learning techniques are used to create switching policies that optimize time or energy in a path tracking task.
Keywords :
control system synthesis; learning (artificial intelligence); mobile robots; optimal control; position control; state estimation; energy optimization; impedance controllers; mobile robot; optimal switching policy learning; path tracking tasks; reinforcement learning techniques; single controller; state estimation; time optimization; tracking control; Computer science; Error correction; Impedance; Linear feedback control systems; Machine learning; Mobile robots; Robotics and automation; State estimation; Velocity control; Wheels;
Conference_Titel :
Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on
Print_ISBN :
0-7803-7398-7
DOI :
10.1109/IRDS.2002.1041507
